# Project export: Sneeze

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: OpenAI Build Week
- Tagline: Step inside a sneeze: a source-linked 3D anatomy atlas built from aligned NIH models, with a deterministic six-stage journey, evidence confidence.
- Devpost: https://devpost.com/software/sneeze-z5f37g
- GitHub: not linked
- Demo: https://ozansozuozgit.github.io/human-moment/
- Video: https://www.youtube.com/embed/bsQEXphh08I?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

I sneezed and wondered how it worked. Now the official part below. A sneeze takes about a second, yet your body manages to coordinate nerves, lungs, pressure, vocal folds, eyelids, and airflow with almost unreasonable confidence. Most explanations reduce that drama to arrows and circles. I wanted to make it feel like you could step inside the moment instead. Human / Moment turns a sneeze into an interactive 3D anatomy experience. At last: a sneeze you can pause without needing a tissue.

### What it does

Human / Moment is a source-linked 3D journey through six stages of a sneeze: Trigger Neural signal Inspiration Compression Release Recovery Users can play a slowed 72-second sequence, scrub through time, jump between stages, orbit the anatomy, isolate body systems, adjust skin opacity, and inspect where each structure and claim comes from. The experience uses aligned NIH Human Reference Atlas geometry for the body surface, lungs, trachea, larynx, mouth, and eye. Neural signals, pressure, diaphragm motion, eyelid closure, and airflow are clearly labeled as explanatory schematics—not fake “perfectly measured” animation. How I built it Codex built the app with React, TypeScript, Vite, Three.js, React Three Fiber, and Drei. The anatomy models come from the NIH Human Reference Atlas and are compressed with Meshopt for faster browser delivery while preserving the decoded geometry. Challenges I ran into The hardest part was making it visually impressive without pretending biology is more certain than it is. And telling codex what to do while worrying if Tibo would reset or not Accomplishments that I'm proud of I made it sneeze What I learned How sneezing works

### What's next

Not much, I already sneezed

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- OpenAI (technology) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.